Related papers: Most Ligand-Based Classification Benchmarks Reward…

In this paper, we investigate potential biases in datasets used to make drug binding predictions using machine learning. We investigate a recently published metric called the Asymmetric Validation Embedding (AVE) bias which is used to…

Current unlearning metrics for generative models evaluate success based on reference responses or classifier outputs rather than assessing the core objective: whether the unlearned model behaves indistinguishably from a model that never saw…

In weakly supervised learning, unbiased risk estimator(URE) is a powerful tool for training classifiers when training and test data are drawn from different distributions. Nevertheless, UREs lead to overfitting in many problem settings when…

The primary objective of most lead optimization campaigns is to enhance the binding affinity of ligands. For large molecules such as antibodies, identifying mutations that enhance antibody affinity is particularly challenging due to the…

A shortcoming of black-box supervised learning models is their lack of interpretability or transparency. To facilitate interpretation, post-hoc global variable importance measures (VIMs) are widely used to assign to each predictor or input…

Likelihood-to-evidence ratio estimation is usually cast as either a binary (NRE-A) or a multiclass (NRE-B) classification task. In contrast to the binary classification framework, the current formulation of the multiclass version has an…

The accurate screening of candidate drug ligands against target proteins through computational approaches is of prime interest to drug development efforts. Such virtual screening depends in part on methods to predict the binding affinity…

Despite the predictive performance of Analogy-Based Estimation (ABE) in generating better effort estimates, there is no consensus on how to predict the best number of analogies, and which adjustment technique produces better estimates. This…

Offline reinforcement learning restricts the learning process to rely only on logged-data without access to an environment. While this enables real-world applications, it also poses unique challenges. One important challenge is dealing with…

LIT-PCBA is widely used to benchmark virtual screening models, but our audit reveals that it is fundamentally compromised. We find extensive data leakage and molecular redundancy across its splits, including 2D-identical ligands within and…

Excessive reuse of test data has become commonplace in today's machine learning workflows. Popular benchmarks, competitions, industrial scale tuning, among other applications, all involve test data reuse beyond guidance by statistical…

Classification, the process of assigning a label (or class) to an observation given its features, is a common task in many applications. Nonetheless in most real-life applications, the labels can not be fully explained by the observed…

Active Learning for discriminative models has largely been studied with the focus on individual samples, with less emphasis on how classes are distributed or which classes are hard to deal with. In this work, we show that this is harmful.…

Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this paper, we identify one cause of overfitting related to current…

The repeated community-wide reuse of test sets in popular benchmark problems raises doubts about the credibility of reported test-error rates. Verifying whether a learned model is overfitted to a test set is challenging as independent test…

The literature on "benign overfitting" in overparameterized models has been mostly restricted to regression or binary classification; however, modern machine learning operates in the multiclass setting. Motivated by this discrepancy, we…

Although numerous methods to reduce the overfitting of convolutional neural networks (CNNs) exist, it is still not clear how to confidently measure the degree of overfitting. A metric reflecting the overfitting level might be, however,…

While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the consistency between the final result and the ground truth,…

Visual entailment (VE) is to recognize whether the semantics of a hypothesis text can be inferred from the given premise image, which is one special task among recent emerged vision and language understanding tasks. Currently, most of the…

Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discrimination and can be more difficult to detect and mitigate. A clear…